Forward perturbation algorithm for a general class of recurrent network

Proceedings of the International Joint Conference on Neural Networks

Volumn 4, Issue , 2001, Pages 2626-2631

  De Jesus O ^a   Hagan, M T ^a  

^a Oklahoma State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; COMPUTER SIMULATION; ERROR ANALYSIS; LEARNING ALGORITHMS; PARTIAL DIFFERENTIAL EQUATIONS; PERTURBATION TECHNIQUES; TRANSFER FUNCTIONS; VECTORS;

BACKPROPAGATION THROUGH TIME; FORWARD PERTURBATION; GRADIENT DESCENT METHOD; LAYERED DIGITAL DYNAMIC NETWORK;

RECURRENT NEURAL NETWORKS;

EID: 0034875838     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Backpropagation through time for a general class of dynamic network
2. Training recurrent networks for filtering and control
3. Identification and control for dynamic systems using neural networks
4. Backpropagation through time: What it is and how to do it
5. A learning algorithm for continually running fully recurrent neural networks
6. Neurocontrol using dynamic learning
7. Training recurrent networks